(112 days)
Manual Defibrillation:
Indications: Manual defibrillation is indicated for the termination of certain potentially fatal arrhythmias, such as ventricular fibrillation and symptomatic ventricular tachycardia. Delivery of this energy in the synchronized mode is a method for treating atrial fibrillation, atrial flutter, paroxysmal supraventricular tachycardia, and, in relatively stable patients, ventricular tachycardia.
Contraindications: Defibrillation is contraindicated in the treatment of Pulseless Electrical Activity (PEA), such as idioventricular or ventricular escape rhythms, and in the treatment of asystole.
Automated External Defibrillation:
Indications: AED mode is to be used only on patients in cardiopulmonary arrest. The patient must be unconscious, pulseless, and not breathing normally before using the defibrillator to analyze the patient's ECG rhythm. In AED mode, the LIFEPAK 15 monitor/defibrillator is not intended for use on pediatric patients less than 8 years old.
Noninvasive Pacing:
Indications: Noninvasive pacing is indicated for symptomatic bradycardia in patients with a pulse.
Contraindications: Noninvasive pacing is contraindicated for the treatment of ventricular fibrillation and asystole.
12-lead Electrocardiography:
Indications: The 12-lead electrocardiogram is used to identify, diagnose and treat patients with cardiac disorders and is useful in the early detection and prompt treatment of patients with acute ST-elevation myocardial infarction (STEMI).
Pulse Oximetry:
Indications: Pulse Oximetry is indicated for use in any patient who is at risk of developing hypoxemia, carboxyhemoglobinemia, or methemoglobinemia. SpO2 monitoring may be used during no motion and motion conditions, and in patients who are well or poorly perfused. SpCO and SpMet accuracies have not been validated under motion or low perfusion conditions.
Noninvasive Blood Pressure Monitoring:
Indications: Noninvasive blood pressure monitoring is intended for detection of hypertension or hypotension and monitoring BP trends in patient conditions such as, but not limited to, shock, acute dysrhythmia, or major fluid imbalance.
End-Tidal CO2 monitoring:
Indications: EtCO2 monitoring is used to detect trends in the level of expired CO2. It is used for monitoring breathing efficacy and treatment effectiveness in acute cardiopulmonary care, for example, to determine if adequate compressions are being performed during CPR or to rapidly detect whether an endotracheal tube has been placed successfully.
Invasive Pressure Monitoring:
Indications: Invasive pressure monitoring is indicated for use in patients who require continuous monitoring of physiological pressures in order to rapidly assess changes in the patient's condition or response to therapy. It may also be used to aid in medical diagnosis.
Temperature Monitoring:
Indications: Temperature monitoring is indicated for use in patients who require continuous monitoring of body temperature.
The LIFEPAK 15 monitor/defibrillator is a complete acute cardiac care response system designed for basic life support (BLS) and advanced life support (ALS) patient management protocols. The LIFEPAK 15 monitor/defibrillator was designed for use in a variety of hospital and pre-hospital settings including emergency rooms, catheterization laboratories, electrophysiology laboratories, crash carts, operating rooms, and ground ambulances. Features of the LIFEPAK 15 monitor/defibrillator include manual and automated external defibrillation, noninvasive pacing, ECG monitoring (3-lead. 7-lead and interpretive 12-Lead), pulse oximetry (SpO2, SpCO, and SpMet), synchronized cardioversion, noninvasive blood pressure monitoring, end-tidal CO2 monitoring, invasive pressure monitoring, and temperature monitoring. The LIFEPAK 15 monitor/defibrillator is powered by rechargeable lithium-ion batteries or from AC power sources via an AC power adapter or DC power sources via a DC power adapter. The primary difference between the proposed LIFEPAK 15 monitor/defibrillator and the previously cleared predicate device is a combination of software and hardware modifications completed to support component obsolescence. The proposed LIFEPAK 15 monitor/defibrillator includes the same monitoring features, defibrillation waveform, pacing waveform, and Shock Advisory System™ algorithm as the previously cleared predicate device. Additionally, there are no changes to the intended use or indications for use of the previously cleared predicate device.
The provided text is a 510(k) Premarket Notification for the Physio-Control LIFEPAK 15 monitor/defibrillator. The document focuses on demonstrating substantial equivalence to a previously cleared device, primarily due to software and hardware modifications for component obsolescence. It does not provide detailed acceptance criteria or a specific study demonstrating performance against such criteria for the entire device's functionalities in the context of an AI/algorithm-driven medical device submission.
However, based on the information provided regarding the "Shock Advisory System™ algorithm," we can infer the aspects that would typically involve performance criteria for an automated external defibrillator (AED) algorithm.
Here's an attempt to answer your questions based on the available information, noting that much of the specific detail for AI/algorithm performance is not present in this 510(k) submission, as it predates the widespread regulatory focus on standalone AI algorithm performance studies. The Shock Advisory System™ algorithm mentioned is likely a rule-based algorithm rather than a modern AI/ML algorithm.
1. A table of acceptance criteria and the reported device performance
The document states: "The proposed LIFEPAK 15 monitor/defibrillator includes the same monitoring features, defibrillation waveform, pacing waveform, and Shock Advisory System™ algorithm as the previously cleared predicate device."
This implies that the performance of the Shock Advisory System™ algorithm is assumed to be equivalent to the predicate device. For AED algorithms, typical acceptance criteria would involve sensitivity (true positive rate for shockable rhythms) and specificity (true negative rate for non-shockable rhythms). While specific numerical acceptance criteria are not presented in this document for the current submission, for similar AED algorithms, these often fall within ranges like:
| Performance Metric | Acceptance Criteria (Typical for AED Algorithms) | Reported Device Performance (Implied from Substantial Equivalence) |
|---|---|---|
| Shockable Rhythm Sensitivity (e.g., Ventricular Fibrillation) | > 90% or >95% | Substantially equivalent to predicate (K082937, K103567), which met standards at their time of clearance. |
| Non-Shockable Rhythm Specificity (e.g., Asystole, Normal Sinus Rhythm) | > 90% or >95% | Substantially equivalent to predicate (K082937, K103567), which met standards at their time of clearance. |
Study Proving Acceptance Criteria:
The document states: "No human clinical studies were submitted as part of this 510(k) Premarket Notification." Instead, the submission relies on "Performance Testing" including:
- Design Requirements Testing
- Hardware Verification
- Software Performance
- Electrical Safety and Electromagnetic Compatibility
- Design Validation via Animal Studies and Simulated Use Testing
The core claim is substantial equivalence to previously cleared LIFEPAK 15 monitor/defibrillators (K082937, K103567). The performance of the Shock Advisory System™ algorithm is explicitly stated as unchanged from the predicate device. Therefore, the "study" proving acceptance criteria for the algorithm's performance would have been conducted for the predicate devices, and the current submission relies on that prior clearance and the assertion that the algorithm itself has not changed.
2. Sample size used for the test set and the data provenance (e.g. country of origin of the data, retrospective or prospective)
Not provided in this document. Information on test set size and data provenance for the Shock Advisory System™ algorithm would have been part of the original 510(k) submission for the predicate devices. This document explicitly states: "No human clinical studies were submitted as part of this 510(k) Premarket Notification."
3. Number of experts used to establish the ground truth for the test set and the qualifications of those experts (e.g. radiologist with 10 years of experience)
Not provided in this document. This information would be specific to the ground truth establishment for the predicate device's algorithm validation.
4. Adjudication method (e.g. 2+1, 3+1, none) for the test set
Not provided in this document. This information would be specific to the ground truth establishment for the predicate device's algorithm validation.
5. If a multi reader multi case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance
No MRMC study was done or reported in this 510(k) submission. The Shock Advisory System™ algorithm in an AED is typically a standalone algorithm designed to automatically detect shockable rhythms, rather than an AI-assisted interpretation tool for human readers in the context of MRMC studies. The device is intended for use by trained medical personnel, including those using the "Automated External Defibrillation" mode, which implies the algorithm is acting as a decision-maker (shock/no shock) rather than an assistant to a human interpreter in the sense of a diagnostic imaging AI.
6. If a standalone (i.e. algorithm only without human-in-the-loop performance) was done
Yes, for the Shock Advisory System™ algorithm, its function in AED mode is inherently standalone in its determination of whether a rhythm is shockable or not. The document states: "Automated External Defibrillation: AED mode is to be used only on patients in cardiopulmonary arrest. The patient must be unconscious, pulseless, and not breathing normally before using the defibrillator to analyze the patient's ECG rhythm." This "analysis" is performed by the algorithm. The performance of this standalone algorithm would have been assessed during the predicate device's clearance. This 510(k) asserts the algorithm is unchanged.
7. The type of ground truth used (expert consensus, pathology, outcomes data, etc)
Not explicitly stated in this document. For AED algorithms, ground truth for rhythm classification (e.g., ventricular fibrillation, asystole, normal sinus rhythm) is typically established by:
- Expert Consensus on ECG Tracings: Review by cardiologists or emergency physicians.
- Simulated Rhythms: Using synthesized or recorded rhythm libraries with known classifications.
- Clinical Outcomes/Events: Correlation with actual patient response to therapy, though less direct for algorithm validation.
It's highly probable that expert consensus on ECG tracings was used for the predicate device.
8. The sample size for the training set
Not provided in this document. This information would be specific to the development and validation of the Shock Advisory System™ algorithm for the predicate devices. Modern AI/ML algorithms often have very large training sets; for the kind of algorithms in AEDs cleared in 2009/2011, training sets might have been smaller, focusing on diverse representations of specific arrhythmias.
9. How the ground truth for the training set was established
Not provided in this document. Similar to question 7, ground truth for the training set (if applicable, as the algorithm might be rule-based rather than machine learning trained) would have been established by expert review of ECG tracings or use of labeled rhythm databases.
§ 870.5310 Automated external defibrillator system.
(a)
Identification. An automated external defibrillator (AED) system consists of an AED and those accessories necessary for the AED to detect and interpret an electrocardiogram and deliver an electrical shock (e.g., battery, pad electrode, adapter, and hardware key for pediatric use). An AED system analyzes the patient's electrocardiogram, interprets the cardiac rhythm, and automatically delivers an electrical shock (fully automated AED), or advises the user to deliver the shock (semi-automated or shock advisory AED) to treat ventricular fibrillation or pulseless ventricular tachycardia.(b)
Classification. Class III (premarket approval)(c)
Date PMA or notice of completion of PDP is required. A PMA will be required to be submitted to the Food and Drug Administration by April 29, 2015, for any AED that was in commercial distribution before May 28, 1976, or that has, by April 29, 2015, been found to be substantially equivalent to any AED that was in commercial distribution before May 28, 1976. A PMA will be required to be submitted to the Food and Drug Administration by April 29, 2015, for any AED accessory described in paragraph (a) that was in commercial distribution before May 28, 1976, or that has, by April 29, 2015, been found to be substantially equivalent to any AED accessory described in paragraph (a) that was in commercial distribution before May 28, 1976. Any other AED and AED accessory described in paragraph (a), shall have an approved PMA or declared completed PDP in effect before being placed in commercial distribution.